Proposal of Awakening Behavior Detection System using Neural Network

H. Satoh, F. Takeda, Y. Saeki, R. Ikeda, and Y. Shiraishi (Japan)


Awakening behavior detection, Neural network, Fallingfrom bed, Intelligent systems


The increase of accidents caused by falling from the bed in care facilities or hospitals is of great concern. Especially the senile or physically disabled elderly are injured by such accidents. To prevent the accidents from occurring, we pro pose an awakening behavior detection system using a neu ral network (NN). The proposed system detects when they almost fall from the bed, and makes it possible to lessen the burden of caregivers or nurses. The system uses pic tures captured with the universal serial bus (USB) camera for detection without trespassing. In this paper, the system classifies their behavior into five states. Namely, they are lying in the bed, being sitting up in the bed, sitting in the bed, almost falling from the bed, and having fallen from the bed, respectively. At first, the experimental apparatus of the proposed system is designed and assembled. Then, the USB camera in the system is selected by testing one’s performance in dark room and capturing area. As experi mental results, the effectiveness of the proposed system is verified in the laboratory level.

Important Links:

Go Back